> For the complete documentation index, see [llms.txt](https://developers.oxylabs.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developers.oxylabs.io/api-targets/cn/llm-he-ai/gemini.md). # Gemini 该 `gemini` 源可让您向 Google Gemini 提交提示词并接收已解析的结构化响应，包括纯文本和 Markdown 答案。 ## 请求示例 以下代码示例展示如何提交提示词并检索带有解析结果的 Gemini 响应。 {% tabs %} {% tab title="cURL" %} ```bash curl 'https://realtime.oxylabs.io/v1/queries' \ --user 'USERNAME:PASSWORD' \ -H 'Content-Type: application/json' \ -d '{ "source": "gemini", "prompt": "best supplements for better sleep", "parse": true, "geo_location": "United States" }' ``` {% endtab %} {% tab title="Python" %} ```python import requests from pprint import pprint # Structure payload. payload = { 'source': 'gemini', 'prompt': 'best supplements for better sleep', 'parse': True, 'geo_location': "United States" } # Get response. response = requests.request( 'POST', 'https://realtime.oxylabs.io/v1/queries', auth=('USERNAME', 'PASSWORD'), json=payload, ) # Print prettified response to stdout. pprint(response.json()) ``` {% endtab %} {% tab title="Node.js" %} ```js const https = require("https"); const username = "USERNAME"; const password = "PASSWORD"; const body = { source: "gemini", prompt: "best supplements for better sleep", parse: true, geo_location: "United States" }; const options = { hostname: "realtime.oxylabs.io", path: "/v1/queries", method: "POST", headers: { "Content-Type": "application/json", Authorization: "Basic " + Buffer.from(`${username}:${password}`).toString("base64"), }, }; const request = https.request(options, (response) => { let data = ""; response.on("data", (chunk) => { data += chunk; }); response.on("end", () => { const responseData = JSON.parse(data); console.log(JSON.stringify(responseData, null, 2)); }); }); request.on("error", (error) => { console.error("Error:", error); }); request.write(JSON.stringify(body)); request.end(); ``` {% endtab %} {% tab title="URL" %} ``` https://realtime.oxylabs.io/v1/queries?source=gemini&prompt=best%20supplements%20for%20better%20sleep&parse=true&geo_location=United%20States&access_token=12345abcde ``` {% endtab %} {% tab title="PHP" %} ```php 'gemini', 'prompt' => 'best supplements for better sleep', 'parse' => true, 'geo_location' => "United States" ); $ch = curl_init(); curl_setopt($ch, CURLOPT_URL, "https://realtime.oxylabs.io/v1/queries"); curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($params)); curl_setopt($ch, CURLOPT_POST, 1); curl_setopt($ch, CURLOPT_USERPWD, "USERNAME" . ":" . "PASSWORD"); $headers = array(); $headers[] = "Content-Type: application/json"; curl_setopt($ch, CURLOPT_HTTPHEADER, $headers); $result = curl_exec($ch); echo $result; if (curl_errno($ch)) { echo 'Error:' . curl_error($ch); } curl_close($ch); ``` {% endtab %} {% tab title="Go" %} ```go package main import ( "bytes" "encoding/json" "fmt" "io/ioutil" "net/http" ) func main() { const Username = "USERNAME" const Password = "PASSWORD" payload := map[string]interface{}{ "source": "gemini", "prompt": "best supplements for better sleep", "parse": true, "geo_location": "United States", } jsonValue, _ := json.Marshal(payload) client := &http.Client{} request, _ := http.NewRequest("POST", "https://realtime.oxylabs.io/v1/queries", bytes.NewBuffer(jsonValue), ) request.SetBasicAuth(Username, Password) response, _ := client.Do(request) responseText, _ := ioutil.ReadAll(response.Body) fmt.Println(string(responseText)) } ``` {% endtab %} {% tab title="C#" %} ```csharp using System; using System.Collections.Generic; using System.Net.Http; using System.Net.Http.Json; using System.Threading.Tasks; namespace OxyApi { class Program { static async Task Main() { const string Username = "USERNAME"; const string Password = "PASSWORD"; var parameters = new { source = "gemini", prompt = "best supplements for better sleep", parse = true, geo_location = "United States" }; var client = new HttpClient(); Uri baseUri = new Uri("https://realtime.oxylabs.io"); client.BaseAddress = baseUri; var requestMessage = new HttpRequestMessage(HttpMethod.Post, "/v1/queries"); requestMessage.Content = JsonContent.Create(parameters); var authenticationString = $"{Username}:{Password}"; var base64EncodedAuthenticationString = Convert.ToBase64String(System.Text.ASCIIEncoding.UTF8.GetBytes(authenticationString)); requestMessage.Headers.Add("Authorization", "Basic " + base64EncodedAuthenticationString); var response = await client.SendAsync(requestMessage); var contents = await response.Content.ReadAsStringAsync(); Console.WriteLine(contents); } } } ``` {% endtab %} {% tab title="Java" %} ```java package org.example; import okhttp3.*; import org.json.JSONObject; import java.util.concurrent.TimeUnit; public class Main implements Runnable { private static final String AUTHORIZATION_HEADER = "Authorization"; public static final String USERNAME = "USERNAME"; public static final String PASSWORD = "PASSWORD"; public void run() { JSONObject jsonObject = new JSONObject(); jsonObject.put("source", "gemini"); jsonObject.put("prompt", "best supplements for better sleep"); jsonObject.put("parse", true); jsonObject.put("geo_location", "United States"); Authenticator authenticator = (route, response) -> { String credential = Credentials.basic(USERNAME, PASSWORD); return response .request() .newBuilder() .header(AUTHORIZATION_HEADER, credential) .build(); }; var client = new OkHttpClient.Builder() .authenticator(authenticator) .readTimeout(180, TimeUnit.SECONDS) .build(); var mediaType = MediaType.parse("application/json; charset=utf-8"); var body = RequestBody.create(jsonObject.toString(), mediaType); var request = new Request.Builder() .url("https://realtime.oxylabs.io/v1/queries") .post(body) .build(); try (var response = client.newCall(request).execute()) { if (response.body() != null) { try (var responseBody = response.body()) { System.out.println(responseBody.string()); } } } catch (Exception exception) { System.out.println("Error: " + exception.getMessage()); } System.exit(0); } public static void main(String[] args) { new Thread(new Main()).start(); } } ``` {% endtab %} {% tab title="JSON" %} ```json { "source": "gemini", "prompt": "best supplements for better sleep", "parse": true, "geo_location": "United States" } ``` {% endtab %} {% endtabs %} {% hint style="info" %} **注意：** 所有 LLM 源默认启用 JavaScript 渲染。您无需在请求负载中包含渲染参数。 {% endhint %} 我们的示例使用同步 [**Realtime**](/products/cn/web-scraper-api/integration-methods/realtime.md) 集成方式。如果您想使用 [**Proxy Endpoint**](/products/cn/web-scraper-api/integration-methods/proxy-endpoint.md) 或异步 [**Push-Pull**](/products/cn/web-scraper-api/integration-methods/push-pull.md) 集成（包括 [批量查询](/products/cn/web-scraper-api/integration-methods/push-pull.md#batch-query)），请参阅 [**集成方法**](/products/cn/web-scraper-api/integration-methods.md) 部分。 ### 请求参数 抓取 Gemini 的基本设置和自定义选项。
参数说明默认值
source设置抓取目标。使用 gemini.–
prompt要提交给 Gemini 的提示词或问题。必须少于 8000 个字符。–
parse设为 true 以获取结构化 JSON 数据。false
geo_location指定用于路由请求的国家/地区。 更多信息.–
browser_instructions渲染 JavaScript 时可选的自定义浏览器指令。 更多信息.–
callback_url您的回调端点的 URL。 更多信息–
\- 必填参数 ## 结构化数据 网页爬虫API 能够提取包含 Gemini 输出的 JSON 对象，从而提供结果页面中各种元素的结构化数据。
gemini 结构化输出 ```json { "results": [ { "job_id": "7470031540181837825", "status_code": 200, "url": "https://gemini.google.com/app/ca6b069d5af5c809", "content": { "prompt": "best supplements for better sleep", "response_text": "If you are tossing and turning, you are definitely not alone. The supplement aisle is packed with options promising to help you drift off, but they generally fall into a few different categories based on how they actually affect your body. Here...", "markdown_text": "If you are tossing and turning, you are definitely not alone. The supplement aisle is packed with options promising to help you drift off, but they generally fall into a few different categories based on how they actually affect your body.\n\n Here...", "citations": [ { "title": "Hartford HealthCare", "url": "https://hartfordhealthcare.org/about-us/news-press/news-detail?articleId=66180", "text": "Can These 3 Supplements Really Improve Your Sleep? | Hartford HealthCare | CT", "description": "- Valerian root. This herbal sleep option likely works by acting on GABA receptors in the brain, just like magnesium. \"But it's not without side effects,\" says ..." }, { "title": "BBC Good Food", "url": "https://www.bbcgoodfood.com/review/best-sleep-supplements#:~:text=It's%20easy%20to%20get%20enough,a%20role%20in%20sleep%20regulation.", "text": "The best sleep supplements 2026 – tried and tested - BBC Good Food", "description": "It's easy to get enough through diet, but if you are looking to supplement, the NRV is around 300mg, and look for magnesium glycinate which has been shown to ..." }, { "title": "PMC - NIH", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11082867/#:~:text=Melatonin%20is%20a%20hormone%20produced,promotes%20relaxation%20and%20reduced%20alertness.", "text": "Current Evidence on Common Dietary Supplements for Sleep Quality - PMC - NIH", "description": "Melatonin is a hormone produced by the pineal gland in the brain and plays a critical role in regulation of the sleep-wake cycle. The pineal gland begins ..." }, ... ], "parse_status_code": 12000 } } ] } ```
{% hint style="warning" %} 响应的组成可能因查询是从 **桌面设备** 或 **移动设备** 发起而异。 {% endhint %} ### 输出数据字典 所有 LLM 目标均返回相同的顶级 `job` 和 `results[]` 封装。有关完整的元数据参考，请参阅 [LLM 和 AI](/api-targets/cn/llm-he-ai.md) 。 下表展示 Gemini 特有的 `results[].content` 字段：
字段名称说明类型
prompt已提交的提示词。字符串
raw流式响应中的原始数据。数组
response_textGemini 返回的纯文本响应。字符串
markdown_textMarkdown 格式的完整响应。字符串
citations响应中引用的来源。每个对象包含 title, url, text和 description.数组
parse_status_code12000 – 成功。否则，解析器未能提取部分或全部结构化字段。整数
model用于生成响应的 AI 模型。字符串
– 条件性返回，仅当内容存在于 LLM 的响应中时返回。 --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://developers.oxylabs.io/api-targets/cn/llm-he-ai/gemini.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.